{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/text-classification/papers/37","list_of":"/task/text-classification","task":"Text Classification","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":37,"pages_in_order":37,"rows_per_page":100,"rows":[3601,3635],"of":3635,"counts":{"archive_papers_tagged":3635,"with_a_code_link":1308,"where_syntology_ran_a_sample":272,"not_listed_spam_title":0,"listed":3635,"listed_where_code_ran":272,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":219,"every_run_a_failure_of_syntologys_instrument":53,"listed_with_a_run_with_no_instrument_failure":219,"listed_every_run_a_failure_of_syntologys_instrument":53,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/text-classification","prev":"/task/text-classification/papers/36","next":null,"papers":[{"url":null,"slug":"toward-automatically-assembling-hittite","title":"Toward Automatically Assembling Hittite-Language Cuneiform Tablet Fragments into Larger Texts","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unt-a-supervised-synergistic-approach-to","title":"UNT: A Supervised Synergistic Approach to Semantic Text Similarity","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"active-learning-for-coreference-resolution-1","title":"Active Learning for Coreference Resolution","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"effect-of-small-sample-size-on-text","title":"Effect of small sample size on text categorization with support vector machines","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-from-bullying-traces-in-social-media","title":"Learning from Bullying Traces in Social Media","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"mining-wisdom","title":"Mining wisdom","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"modeling-coherence-in-esol-learner-texts","title":"Modeling coherence in ESOL learner texts","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"on-improving-the-accuracy-of-readability","title":"On Improving the Accuracy of Readability Classification using Insights from Second Language Acquisition","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"portable-features-for-classifying-emotional","title":"Portable Features for Classifying Emotional Text","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unified-expectation-maximization","title":"Unified Expectation Maximization","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-french-fairy-tale-corpus-syntactically-and","title":"A French Fairy Tale Corpus syntactically and semantically annotated","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"annotating-opinions-in-german-political-news","title":"Annotating Opinions in German Political News","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"feature-discovery-for-diachronic-register","title":"Feature Discovery for Diachronic Register Analysis: a Semi-Automatic Approach","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"french-and-german-corpora-for-audience-based","title":"French and German Corpora for Audience-based Text Type Classification","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-k-nearest-neighbor-efficacy-for","title":"Improving K-Nearest Neighbor Efficacy for Farsi Text Classification","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"measuring-interlanguage-native-language","title":"Measuring Interlanguage: Native Language Identification with L1-influence Metrics","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"nlp-challenges-for-eunomos-a-tool-to-build","title":"NLP Challenges for Eunomos a Tool to Build and Manage Legal Knowledge","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"statistical-section-segmentation-in-free-text","title":"Statistical Section Segmentation in Free-Text Clinical Records","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-blademistress-corpus-from-talk-to-action","title":"The BladeMistress Corpus: From Talk to Action in Virtual Worlds","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-twins-corpus-of-museum-visitor-questions","title":"The Twins Corpus of Museum Visitor Questions","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"vreselijk-mooi-terribly-beautiful-a","title":"``Vreselijk mooi!'' (terribly beautiful): A Subjectivity Lexicon for Dutch Adjectives.","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-lingual-genre-classification","title":"Cross-Lingual Genre Classification","date":"2012-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"discourse-type-clustering-using-pos-n-gram","title":"Discourse Type Clustering using POS n-gram Profiles and High-Dimensional Embeddings","date":"2012-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"experimenting-with-distant-supervision-for","title":"Experimenting with Distant Supervision for Emotion Classification","date":"2012-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"topic-classification-of-blog-posts-using","title":"Topic Classification of Blog Posts Using Distant Supervision","date":"2012-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"visualising-linguistic-evolution-in-academic","title":"Visualising Linguistic Evolution in Academic Discourse","date":"2012-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-feature-selection-method-for-multivariate","title":"A Feature Selection Method for Multivariate Performance Measures","date":"2011-03-05","arxiv_id":"1103.1013","repositories_listed":0,"syntology":null},{"url":null,"slug":"collective-classification-of-textual","title":"Collective Classification of Textual Documents by Guided Self-Organization in T-Cell Cross-Regulation Dynamics","date":"2011-02-04","arxiv_id":"1102.1027","repositories_listed":0,"syntology":null},{"url":null,"slug":"universal-kernels-on-non-standard-input","title":"Universal Kernels on Non-Standard Input Spaces","date":"2010-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"dirichlet-bernoulli-alignment-a-generative","title":"Dirichlet-Bernoulli Alignment: A Generative Model for Multi-Class Multi-Label Multi-Instance Corpora","date":"2009-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"modeling-social-annotation-data-with-content","title":"Modeling Social Annotation Data with Content Relevance using a Topic Model","date":"2009-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-the-semantic-correlation-an","title":"Learning the Semantic Correlation: An Alternative Way to Gain from Unlabeled Text","date":"2008-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"regularized-learning-with-networks-of","title":"Regularized Learning with Networks of Features","date":"2008-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-randomized-algorithm-for-large-scale","title":"A Randomized Algorithm for Large Scale Support Vector Learning","date":"2007-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multiple-instance-active-learning","title":"Multiple-Instance Active Learning","date":"2007-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"1b1797c1991bd3c6b428ea20b98a86b1393975445a9440709c965fd4ce5b3493","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}